Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal JITK (Jurnal Ilmu Pengetahuan dan Komputer) Jurnal Nasional Komputasi dan Teknologi Informasi
Bimantyoso Hamdikatama
Universitas Muhammadiyah Surakarta
Aerospace Engineering Automotive Engineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering Neuroscience Transportation

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
BEYOND ALGORITHMS: AN INTEGRATED APPROACH TO FAKE NEWS DETECTION USING MACHINE LEARNING TECHNIQUES Bimantyoso Hamdikatama
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 10 No. 3 (2025): JITK Issue February 2025
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v10i3.6061

Abstract

The internet has become a major source of information, but it also facilitates the rapid spread of fake news, which can significantly influence public opinion and social decisions. While various techniques have been developed for detecting fake news, many studies focus on individual algorithms, which often result in suboptimal performance. This study addresses this gap by comparing machine learning models, including Support Vector Classification (SVC), XGBoost, and a Stacking Ensemble that combines both SVC and XGBoost, to determine the most effective approach for fake news detection. Text preprocessing was performed using IndoBERT, which provides context-aware and semantically rich text representations specifically for the Indonesian language. The evaluation results demonstrate that the Stacking Ensemble outperforms the individual models, achieving an accuracy of 82%, compared to 79% for XGBoost and 78% for SVC. This superior performance is attributed to the complementary strengths of the base models: SVC excels in handling high-dimensional data, while XGBoost effectively manages imbalanced datasets and captures complex feature interactions. The use of IndoBERT further enhances model performance by improving text representation through contextual embeddings. These findings highlight the effectiveness of ensemble learning in enhancing predictive performance and robustness for fake news detection, demonstrating the potential of combining different machine learning techniques with advanced preprocessing methods to achieve more reliable results.
Benchmarking Hyperparameter Variations on Transfer Learning Models for Coral Reefs Classification: A Case Study on Efficientnetv2 and Mobilenetv2 Bimantyoso Hamdikatama; Dedi Gunawan; Kusrini Kusrini
Jurnal Nasional Komputasi dan Teknologi Informasi (JNKTI) Vol 8, No 1 (2025): Februari 2025
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v8i1.8792

Abstract

Abstract - Coral reef recognition using transfer learning models is a critical area of research to enhance automated monitoring and conservation efforts. This study examines the impact of hyperparameter tuning on the performance of two models, EfficientNetV2 and MobileNetV2, in recognizing coral reef conditions such as bleaching, physical damage, and algae overgrowth. Bayesian Optimization is evaluated as an automated hyperparameter tuning method alongside Grid Search, Random Search, and Manual Trial-based approaches. The results reveal that Bayesian Optimization achieves competitive accuracy (up to 0.81) and balances computational efficiency with performance, requiring fewer trials compared to manual optimization. Notably, Bayesian Optimization reduces training time while maintaining high metrics such as Precision and Specificity. These findings highlight the effectiveness of Bayesian Optimization in improving model performance for coral reef recognition, offering a reliable and efficient solution to support conservation decision-making. This approach also demonstrates potential for broader applications in classification and regression tasks.Keywords: EfficientNetV2, MobileNetV2, Optimization, Coral Reefs Abstrak - Pengenalan terumbu karang menggunakan model pembelajaran transfer adalah bidang penelitian yang penting untuk meningkatkan upaya pemantauan dan konservasi otomatis. Penelitian ini menguji dampak penyetelan hyperparameter pada kinerja dua model, EfficientNetV2 dan MobileNetV2, dalam mengenali kondisi terumbu karang seperti pemutihan, kerusakan fisik, dan pertumbuhan berlebih alga. Bayesian Optimization dievaluasi sebagai metode penyetelan hiperparameter otomatis bersama dengan Pencarian Grid, Pencarian Acak, dan pendekatan berbasis Uji Coba Manual. Hasilnya menunjukkan bahwa Bayesian Optimization mencapai akurasi yang kompetitif (hingga 0,81) dan menyeimbangkan efisiensi komputasi dengan kinerja, sehingga membutuhkan lebih sedikit uji coba dibandingkan dengan pengoptimalan manual. Selain itu, Bayesian Optimization mengurangi waktu pelatihan dengan tetap mempertahankan metrik yang tinggi seperti Presisi dan Spesifisitas. Temuan ini menyoroti efektivitas Optimasi Bayesian dalam meningkatkan kinerja model untuk pengenalan terumbu karang, menawarkan solusi yang andal dan efisien untuk mendukung pengambilan keputusan konservasi. Pendekatan ini juga menunjukkan potensi untuk aplikasi yang lebih luas dalam tugas klasifikasi dan regresi.Kata kunci: EfisienNetV2, MobileNetV2, Optimasi, Terumbu Karang
Co-Authors Dedi Gunawan Kusrini Kusrini